Continuous Heartbeat Prediction Using a Face Recognition Algorithm
Bibliographic record
Abstract
Health providers use the ECG machine to get information about the heart. This information plays a significant role since it tells them about the status of the heart. The ECG machine presents this information in a waveform. During the Covid-19 pandemic, all governments have placed numerous rules and policies to protect people from the virus and from spreading it. One of the rules and policies is to prevent touching surfaces in public places. However, in health care centers, touching surfaces can’t be avoided completely since there is a need to touch them or place some wires on the human body such as placing wires to use the ECG machine. In Saudi Arabia, the government has placed a policy in all its buildings, public places, and the private sector to measure the temperature at the entrance. Due to this situation, the idea has come into mind to have a touchless method to measure the heartbeat rate. In this paper, proposing a feasible and reliable method to estimate a continuous heartbeat rate is presented. It uses a face recognition approach to predict the heart pulse continuously in real-time according to colors intensity measurement. Using a segmentation algorithm is involved since the approach takes its input from a video or an image. Several experiments have been conducted on volunteers to verify the obtained results and measure their relative errors. Consequently, the errors are less than 7% which is quite acceptable. At the end of this article, a comparative assessment is performed between the presented approach and some works from literature. This assessment is conducted based on the methodologies being utilized and applied and Mean Absolute Error (MAE). Furthermore, it shows whether those methods require physical contact or not. The obtained results indicate that the implemented system herein outperforms other state-of-the-art methods.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".